© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 177475
    Prev
    Next
    INDEX
    Explanations

    aasta, χει, WriteString, нул, dibagi

    np_acts-logits-general · gemini-2.5-flash-lite

    middle school or business

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rta
    0.53
    os
    0.53
    odon
    0.53
    ü
    0.52
    irte
    0.52
    ne
    0.51
    od
    0.50
    aj
    0.50
    ı
    0.50
    ATION
    0.49
    POSITIVE LOGITS
    λης
    0.57
    Само
    0.47
     পরিশ্রম
    0.47
     aasta
    0.46
    χει
    0.46
    WriteString
    0.46
    롤
    0.44
     нуля
    0.43
     dibagi
    0.43
    არის
    0.43
    Activations Density 0.000%

    No Known Activations